GenAI Developer

☐ Python · Required · 6 hrs

Functions, classes, async, environment management, working with JSON. GenAI tooling is Python-first.

• What is Python? Setup & Your First Program (Python): https://chaduvuko.com/learn/python/what-is-python-setup
• Functions — Defining, Parameters, Return Values (Python): https://chaduvuko.com/learn/python/functions
• Reading & Writing Files (Python): https://chaduvuko.com/learn/python/reading-writing-files
• Exception Handling (Python): https://chaduvuko.com/learn/python/exception-handling

☐ LLM Fundamentals · Required · 4 hrs

How LLMs work (at a conceptual level), tokens, context windows, temperature, top-p. Understanding the tool you're building on.

• What is Generative AI? (AI & Machine Learning): https://chaduvuko.com/learn/ai-ml/generative-ai/what-is-generative-ai
• LLMs — Pretraining, RLHF and Scaling Laws (AI & Machine Learning): https://chaduvuko.com/learn/ai-ml/generative-ai/llms-pretraining-rlhf

☐ REST APIs & HTTP · Required · 3 hrs

Calling OpenAI / Anthropic / Gemini APIs via Python. All LLM providers are API-first.

• Working with APIs — REST, Auth, Pagination, Rate Limits (Data Engineering): https://chaduvuko.com/learn/data-engineering/working-with-apis
• Working with APIs in Python (Python): https://chaduvuko.com/learn/python/working-with-apis-python
• HTTP and HTTPS — The Protocol Powering the Web (Networking): https://chaduvuko.com/learn/networking/http-and-https

☐ Prompt Engineering · Required · 5 hrs

System prompts, few-shot examples, chain-of-thought, structured output (JSON mode), prompt templates. The core applied skill of GenAI development.

• Prompt Engineering (AI & Machine Learning): https://chaduvuko.com/learn/ai-ml/nlp/prompt-engineering

☐ Embeddings · Required · 4 hrs

Text-to-vector conversion, cosine similarity, embedding models (OpenAI, HuggingFace). The foundation of semantic search and RAG.

• Tokenisation and Word Embeddings (AI & Machine Learning): https://chaduvuko.com/learn/ai-ml/nlp/tokenisation-and-embeddings
• Dot Product and Similarity (AI & Machine Learning): https://chaduvuko.com/learn/ai-ml/math-foundations/dot-product-similarity

☐ Vector Databases · Required · 4 hrs

Chroma, Pinecone, pgvector — store and query embeddings at scale. Required for any RAG application.

• Dot Product and Similarity (AI & Machine Learning): https://chaduvuko.com/learn/ai-ml/math-foundations/dot-product-similarity
• RAG — Retrieval-Augmented Generation (AI & Machine Learning): https://chaduvuko.com/learn/ai-ml/nlp/rag-retrieval-augmented-generation

☐ RAG (Retrieval-Augmented) · Required · 8 hrs

Document loading, chunking, retrieval, context injection, hybrid search. RAG is how 90% of enterprise GenAI products are built.

• RAG — Retrieval-Augmented Generation (AI & Machine Learning): https://chaduvuko.com/learn/ai-ml/nlp/rag-retrieval-augmented-generation
• Advanced RAG (AI & Machine Learning): https://chaduvuko.com/learn/ai-ml/generative-ai/advanced-rag

☐ LangChain / LlamaIndex · Required · 6 hrs

Chains, agents, memory, tools, document loaders, output parsers. Frameworks that wire together LLM components.

☐ Fine-tuning Basics · Optional · 8 hrs

Instruction tuning, LoRA, dataset preparation, HuggingFace Trainer. When prompt engineering isn't enough for your domain.

• Fine-Tuning with PEFT — LoRA and Adapters (AI & Machine Learning): https://chaduvuko.com/learn/ai-ml/nlp/peft-lora-adapters
• LLM Fine-Tuning in Practice (AI & Machine Learning): https://chaduvuko.com/learn/ai-ml/generative-ai/llm-fine-tuning
• LLMs — Pretraining, RLHF and Scaling Laws (AI & Machine Learning): https://chaduvuko.com/learn/ai-ml/generative-ai/llms-pretraining-rlhf

☐ Agents & Multi-agent · Required · 8 hrs

Tool-calling agents, memory, planning, LangGraph, CrewAI. Multi-agent orchestration is the cutting edge of production GenAI.

• LLM Agents and Tool Use (AI & Machine Learning): https://chaduvuko.com/learn/ai-ml/nlp/llm-agents-and-tool-use
• Agents and Tool Use (AI & Machine Learning): https://chaduvuko.com/learn/ai-ml/generative-ai/agents-tool-use

☐ Evaluation (RAGAS) · Required · 4 hrs

Faithfulness, answer relevancy, context precision. Measure before you claim your RAG pipeline works.

☐ Production Deployment · Required · 7 hrs

FastAPI wrapper, Docker, streaming responses, latency monitoring, cost tracking, prompt versioning. Moving demos to real products.

• Model Deployment — FastAPI, Docker, K8s (AI & Machine Learning): https://chaduvuko.com/learn/ai-ml/mlops/model-deployment

☐ AI Safety & Guardrails · Recommended · 4 hrs

Input/output filtering, jailbreak prevention, toxicity detection, Guardrails AI. Required for any customer-facing AI product.